大型语言模型会掷骰子吗?探究大型语言模型中的概率分布采样用于行为模拟
Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation
AI总结:
本研究探讨大型语言模型智能体在行为模拟中理解与采样概率分布的能力,发现其能理解概率但采样困难,整合编码工具可部分改善,但仍难以精确模拟人类行为。
摘要:
随着大型语言模型(LLMs)在处理复杂语言任务方面的快速发展,越来越多的研究将LLMs用作智能体,以模拟人类通常表示为马尔可夫决策过程(MDPs)的序贯决策过程。MDPs中的动作遵循特定的概率分布,并需要迭代采样。这引发了关于LLM智能体理解概率分布能力的兴趣,从而通过概率采样引导智能体的行为决策,并生成行为序列。为了回答上述问题,我们将问题分为两个主要方面:已知概率分布的序列模拟和未知概率分布的序列模拟。我们的分析表明,LLM智能体能够理解概率,但在概率采样方面存在困难。通过整合编码工具,它们执行概率采样的能力可以在一定程度上得到提升,但这种采样精度仍然难以使它们作为智能体模拟人类行为。
英文摘要:
With the rapid advancement of large language models (LLMs) for handling complex language tasks, an increasing number of studies are employing LLMs as agents to emulate the sequential decision-making processes of humans often represented as Markov decision-making processes (MDPs). The actions in MDPs adhere to specific probability distributions and require iterative sampling. This arouses curiosity regarding the capacity of LLM agents to comprehend probability distributions, thereby guiding the agent's behavioral decision-making through probabilistic sampling and generating behavioral sequences. To answer the above question, we divide the problem into two main aspects: sequence simulation with known probability distribution and sequence simulation with unknown probability distribution. Our analysis indicates that LLM agents can understand probabilities, but they struggle with probability sampling. Their ability to perform probabilistic sampling can be improved to some extent by integrating coding tools, but this level of sampling precision still makes it difficult to simulate human behavior as agents.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。